Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

using ICDAR2015 dataset train from raw and the model doesn't converge? ICDAR2015 EPO1200 Batch_size 16 不收敛 #381

Open
goseesomething opened this issue Oct 21, 2024 · 2 comments
Open

using ICDAR2015 dataset train from raw and the model doesn't converge? ICDAR2015 EPO1200 Batch_size 16 不收敛 #381

goseesomething opened this issue Oct 21, 2024 · 2 comments

Comments

@goseesomething
Copy link

Does anyone face the problem?

有人遇到這問題嗎?
@DeathGparadise
Copy link

Does anyone face the problem?

有人遇到這問題嗎?

是可以收敛的，你检查一下你数据集的问题，我换了backbone从头训练，大概600多epochs的时候收敛了

@goseesomething
Copy link
Author

goseesomething commented Nov 2, 2024 •
edited
Loading

Does anyone face the problem?
有人遇到這問題嗎?

是可以收敛的，你检查一下你数据集的问题，我换了backbone从头训练，大概600多epochs的时候收敛了

感謝回覆~
後來找到原因了SGD是比較不穩定～的確有時候會不收斂
然後也感謝通知是600多epo左右～我下次再訓會留意這個數字！

然後之前訓沒有找到對的conda list
後來跟著下面凡Issue內容 重整conda list環境就訓得起來了：
#323 這邊的conda list

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
2 participants
@goseesomething @DeathGparadise